> ## Documentation Index
> Fetch the complete documentation index at: https://docs.edgespark.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Minimal human input in EdgeSpark

> Agents should finish the task without interruptions by default, and stop only for login, secret entry, or clearly destructive actions.

EdgeSpark is designed for autonomous agent operation. The default rule is simple: finish the task without interrupting the user.

Stop only when the user must do something personally or when the next step is clearly destructive.

## Bottom line

* Do not stop for normal coding work, schema updates, migrations, config changes, dry runs, testing, logs, or routine deploys.
* Stop for `edgespark login` when the user must open the browser login URL.
* Stop for secret entry when the user must provide the real secret value through EdgeSpark's secure flow.
* Stop when enabling a new social OAuth provider requires the user to prepare provider credentials and external app setup first.
* Stop before clearly destructive actions such as dropping schema, deleting bulk data, deleting secrets, or targeting the wrong project.

## Stop only for these cases

| Case                                                                         | Why stop                                                                                          |
| ---------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- |
| `edgespark login` in an agent or non-TTY session                             | The CLI prints a login URL that the user must open in a browser                                   |
| Set or update a secret value                                                 | The user must enter the real value themselves through the secure secret-entry flow                |
| Enable a new social OAuth provider                                           | The user may need to prepare provider credentials, redirect URLs, and external app settings first |
| Drop tables, columns, or indexes                                             | Destructive schema change                                                                         |
| Run destructive raw SQL or bulk deletes                                      | Can permanently remove data                                                                       |
| Delete a secret                                                              | May break the deployed app immediately                                                            |
| Change `edgespark.toml` `project_id` or otherwise target a different project | May mutate or deploy the wrong project                                                            |
| Make a deploy whose impact is obviously dangerous or not understood yet      | Public projects deploy to the live project URL today                                              |

Never ask the user to paste a secret into chat or terminal output.

## How to ask when you must

* Be brief.
* Explain the exact next action.
* Explain the consequence in plain language.
* Ask one thing, not five.

## Communicating a decision point

> "This step needs your browser. Please open the EdgeSpark login URL and approve it. After that, I can continue."

> "This feature needs a `STRIPE_WEBHOOK_SECRET`. Please add it through EdgeSpark's secure secret-entry flow. Do not paste the value here."

> "To enable Google login, please first prepare the OAuth app in Google and the client credentials it requires. After that, I can update the EdgeSpark auth config."

> "The next command will drop existing table data. That is destructive and may be irreversible. If you want me to continue, I'll run \[action] next."

## See also

<Columns cols={2}>
  <Card title="The harness model" icon="shield" href="/agents/harness">
    What the platform enforces automatically — decisions you never need to make.
  </Card>

  <Card title="Deploy and test loop" icon="rotate" href="/agents/deploy-and-test">
    The current deploy and test workflow, including why dry runs matter before live deploys.
  </Card>

  <Card title="Handling errors" icon="triangle-exclamation" href="/agents/handling-errors">
    How to diagnose and fix errors without stopping for human input.
  </Card>

  <Card title="AGENTS.md reference" icon="file-lines" href="/agents/agents-md">
    How project-specific rules in the instructions file extend these defaults.
  </Card>
</Columns>